MINDFul: A Novel Virtual System Migration Decision-making Framework for Automated Cyber-Resiliency

Abstract

Virtual system migration has revolutionized modern computing. As an advantageous byproduct of virtualization, virtual system migration has allowed for cheaper, more robust cloud management. The selection of a destination host during migration is a key component of migration management. However, there is currently no state-of-the-art, standardized framework for making this decision. Previous work related to automated load balancing is plentiful, but when load balancing is not the primary focus of the cloud management strategy there is a lack of research. We focus on this case, where virtual systems are no longer moved based on some predefined optimization pattern, but rather as single migration events triggered by some alerting mechanism. This is typically seen in cyber-resiliency management systems. The goal of this thesis is to present MINDFul: a novel virtual system migration decision-making framework. MINDFul is then prototyped for a cyber-resiliency management system to facilitate automated resiliency efforts. We demonstrate that MINDFul is a powerful and flexible framework consistent with modern, state-of-the-art efforts in automated cyber-resiliency management.